© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 249951
    Prev
    Next
    INDEX
    Explanations

    brief presentation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    wä
    0.44
    enuh
    0.41
     появление
    0.38
    ophyll
    0.37
    aksanaan
    0.37
     einst
    0.37
    ֖
    0.37
    urface
    0.37
     anxiety
    0.36
    ContentLoaded
    0.36
    POSITIVE LOGITS
     cloudinary
    0.45
     Geç
    0.44
     tặng
    0.42
     Afterward
    0.42
    赟
    0.41
     Rena
    0.41
     paid
    0.40
     أس
    0.40
     Paid
    0.40
    醿
    0.40
    Activations Density 0.000%

    No Known Activations